What is x-impact-checker CLAUDE.md?

Repository instructions for X Impact Checker, a documentation-only Claude skill that evaluates X (formerly Twitter) posts for likely engagement using X's published recommendation rules.

Maintaining the skill's scoring guidance, algorithm references, project conventions, bilingual documentation, and improvement suggestions for posts.

They explain the project structure and evaluation approach so an assistant can update the skill consistently instead of treating it like ordinary application code.

How tonkotsuboy/x-impact-checker configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tonkotsuboy/x-impact-checker. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tonkotsuboy/x-impact-checker/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tonkotsuboy/x-impact-checker

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tonkotsuboy/x-impact-checker/claude-md/github.svg)](https://agentmods.dev/instructions/tonkotsuboy/x-impact-checker/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tonkotsuboy/x-impact-checker/claude-md"><img src="https://agentmods.dev/badge/instructions/tonkotsuboy/x-impact-checker/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tonkotsuboy/x-impact-checker/claude-md"><img src="https://agentmods.dev/badge/instructions/tonkotsuboy/x-impact-checker/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 506 This file is loaded in full into every session.

When invoked 506 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00506	$0.00506
Opus 5.5	$0.00202	$0.00202
Sonnet 5.5	$0.00101	$0.00101
Haiku 4.5	$0.00051	$0.00051

Measured 2mo ago against content hash 914c36e17ecd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

x-impact-checker CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

X Impact Checker is a Claude skill that analyzes X (Twitter) posts for viral potential based on X's official recommendation algorithm.

Purpose: Predict engagement and provide optimization suggestions before posting using X's official recommendation algorithm scoring system

Technology: Documentation-based skill (markdown only, no codebase)

Repository Structure

/
├── .claude/rules/project-conventions.md  # Language and commit standards
├── skills/x-impact-checker/
│   ├── SKILL.md                          # Skill definition and scoring criteria
│   └── references/algorithm-weights.md   # X algorithm reference
├── README.md                             # Bilingual documentation (EN/JP)
└── LICENSE                               # Apache 2.0

Core Components

SKILL.md

Main skill logic with 3-tier scoring system (Core/Extended/Relationship Engagement + Negative Signals), evaluation criteria, and improvement strategies in ❌ Bad / ⚠️ Better / ✅ Best format.

algorithm-weights.md

Technical reference for X's algorithm: engagement signals, weight coefficients from weighted_scorer.rs, conditional logic (VQV threshold), and normalization.

Scoring Architecture

100-point system with penalty dampening:

Final Score = Base Score (0-100) + Penalties (-75 to 0)
Normalized = max(0, min(100, Final Score))

Key characteristics:

Reply (22 points) is highest weighted - conversation drives visibility
Multiple share types distinguished (general/DM/link copy)
Two dwell time types (initial read/continuous engagement)
Videos require 5+ seconds for full score (VQV condition)
Negative signals dampened to prevent over-penalization

Design Decisions

Codeless architecture: Heuristic text analysis, not ML model
Conservative scoring: Unknown elements get baseline scores
Optimization-focused: Pre-publishing tool, not post-hoc analytics
Language-agnostic: Detects input language, responds in same language

Read the full file on GitHub · 60 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 60 lines · 506 tokens per session scan A 914c36e17ecd

Subscribe to this mod's changes

x-impact-checker CLAUDE.md is an instructions file published in the GitHub repository tonkotsuboy/x-impact-checker (37 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 506 tokens to every session, about $0.0020 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Marketing and SEO agent-skills algorithms claude claudecode codex twitter

x-impact-checker CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
x-impact-checker CLAUDE.mdtonkotsuboy/x-impact-checker	Instructions file	37	6mo ago	Apache-2.0	A	506	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

x-impact-checker: Instructions file for Claude Code